DeepSeek V4 Pro 0813 pricing across providers
Across tracked provider offerings, input runs $0.103–$1.65 per million tokens and output $1.20–$8.00 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Baidu at $0.032 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 25 of 25 offerings publish a cache-read rate; 17 of 25 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to DeepSeek V4 Pro 0813
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for DeepSeek V4 Pro 0813
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Baidu promo | fp8 | $0.449 | $1.35 | $0.014 | $0.032 | 100.00% |
| Avian | — | $0.561 | $1.68 | $0.019 | $0.041 | — |
| Streamlake promo | unknown | $0.660 | $1.98 | $0.022 | $0.048 | 100.00% |
| Deepseek | unknown | $0.660 | $1.98 | $0.022 | $0.048 | 100.00% |
| Novita promo | fp8 | $0.990 | $2.97 | $0.033 | $0.072 | 100.00% |
| GMI Cloud promo | fp8 | $1.06 | $3.17 | $0.035 | $0.076 | — |
| Alibaba | unknown | $0.581 | $1.74 | $0.058 | $0.080 | 100.00% |
| Nebius | fp8 | $1.32 | $3.96 | $0.040 | $0.092 | 100.00% |
| Coreweave | fp8 | $1.31 | $3.96 | $0.044 | $0.095 | 100.00% |
| Parasail | fp8 | $1.32 | $3.96 | $0.044 | $0.095 | 100.00% |
| Digitalocean | unknown | $1.32 | $3.96 | $0.044 | $0.095 | — |
| SiliconFlow | fp8 | $1.32 | $3.96 | $0.044 | $0.095 | 100.00% |
| Cloudflare | unknown | $1.32 | $3.96 | $0.044 | $0.095 | 100.00% |
| Hyper | — | $1.44 | $4.31 | $0.048 | $0.104 | — |
| Ionstream | unknown | $0.370 | $2.93 | $0.088 | $0.109 | 100.00% |
| Sail Research | fp4 | $0.675 | $1.20 | $0.098 | $0.117 | 100.00% |
| Wafer | mxfp4 | $0.115 | $4.30 | $0.110 | $0.131 | 100.00% |
| Phala promo | unknown | $0.957 | $2.88 | $0.099 | $0.134 | — |
| Relace | fp4 | $0.103 | $8.00 | $0.100 | $0.140 | 100.00% |
| DeepInfra | — | $1.30 | $2.60 | $0.100 | $0.143 | — |
| Together | unknown | $1.32 | $3.96 | $0.130 | $0.179 | 100.00% |
| Baseten | fp4 | $1.32 | $3.96 | $0.132 | $0.181 | — |
| Atlascloud | fp8 | $1.32 | $3.96 | $0.132 | $0.181 | 100.00% |
| Dekallm | unknown | $1.08 | $3.80 | $0.180 | $0.221 | 100.00% |
| Venice | unknown | $1.65 | $4.95 | $0.165 | $0.226 | — |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.